US8073197B2
Expired / Lapsed
US
⏱️ 0.0 years remaining
Method of tracking objects in a video sequence
Assignee: British Telecommunications PLC
•
Filing: 2006-03-01
•
Granted: 2011-12-06
•
Expires: 2026-03-01
Abstract
Abstract A video surveillance system ( 10 ) comprises a camera ( 25 ), a personal computer (PC) ( 27 ) and a video monitor ( 29 ). Video processing software is provided on the hard disk drive of the PC ( 27 ). The software is arranged to perform a number of processing operations on video data received from the camera, the video data representing individual frames of captured video. In particular, the software is arranged to identify one or more foreground blobs in a current frame, to match the or each blob with an object identified in one or more previous frames, and to track the motion of the or each object as more frames are received. In order to maintain the identity of objects during an occlusion event, an appearance model is generated for blobs that are close to one another in terms of image position. Once occlusion takes place, the respective appearance models are used, in combination with a depth factor representing the depth order of the occluded objects, to segment the resulting group blob into regions which are classified as representing one or other of the merged objects.
Inventors
- 👤 Li-Qun Xu
- 👤 Pere Puig Folch
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-09 10:17
CPC Classifications
G; G06; G06T; G06T7/00; G06T7/20; G06T7/215; G06T7/10; G06T7/194; G06T7/246; G06T7/251; G06T7/277; G06V; G06V10/00; G06V10/20; G06V10/24; G06V20/00; G06V20/50; G06V20/52; G06T2207/00; G06T2207/10; G06T2207/10016
Claims Analysis
Total Claims: 13
Claim 1
Independent Claim
218 words
A method of tracking objects in a video sequence comprising a plurality of frames, each object being defined by a plurality of pixels, the method comprising: (a) identifying, in a first frame, first and second objects; (b) providing first and second appearance models respectively representing the first and second objects; (c) identifying in a second, subsequent, frame, a group object resulting from the merging of the first and second objects due to occlusion; (d) classifying each pixel of the group object as representing either the first or second object, the classification comprising (i) calculating first and second likelihood parameters respectively indicating the correspondence between said pixel's appearance and the first and second appearance models, (ii) applying a first and second weighting factor to the respective likelihood parameters, said weighting factors being respectively based on and indicative of the determined depth order of the first and second objects, and (iii) identifying which of the first and second objects said pixel represents on the basis of the weighted first and second likelihood parameters; wherein the depth order of the first and second objects is determined based on determining in the first frame which of the first and second objects is nearer to a reference position in the first frame or nearer to a reference line extending across the first frame.
Claim 2
Independent Claim
218 words
A method of tracking objects in a video sequence comprising a plurality of frames, each object being defined by a plurality of pixels, the method comprising: (a) identifying, in a first frame, first and second objects; (b) providing first and second appearance models respectively representing the first and second objects; (c) identifying in a second, subsequent, frame, a group object resulting from the merging of the first and second objects due to occlusion; (d) classifying each pixel of the group object as representing either the first or second object, the classification comprising (i) calculating first and second likelihood parameters respectively indicating the correspondence between said pixel's appearance and the first and second appearance models, (ii) applying a first and second weighting factor to the respective likelihood parameters, said weighting factors being respectively based on and indicative of the determined depth order of the first and second objects, and (iii) identifying which of the first and second objects said pixel represents on the basis of the weighted first and second likelihood parameters; wherein the depth order of the first and second objects is determined based on determining in the first frame which of the first and second objects is nearer to a reference position in the first frame or nearer to a reference line extending across the first frame.
Claim 3
Dependent Claim
34 words
A method according to claim 1 , wherein the object nearest the reference position or the reference line is assigned to a first level and the other object is assigned to a second level.
Claim 4
Dependent Claim
68 words
A method according to claim 2 , wherein the depth order is verified by analysing the change in the number of pixels defining the respective first and second objects over a plurality of frames generated prior to the second frame, the depth order of the objects being interchanged if the number of pixels defining object assigned to the first level has the greatest change in number of pixels.
Claim 5
Dependent Claim
26 words
A method according to claim 1 , wherein the first and second appearance models represent the respective colour distribution of the first and second candidate objects.
Claim 6
Dependent Claim
36 words
A method according to claim 1 , wherein the first and second appearance models represent a combination of the respective (a) colour distribution of, and (b) edge density information for, the first and second candidate objects.
Claim 7
Dependent Claim
25 words
A method according to claim 5 , wherein the edge density information is derived from a Sobel edge detection operation performed on the candidate object.
Claim 8
Dependent Claim
35 words
A method according to claim 1 , wherein step (c) comprises identifying a new candidate object whose frame position partially overlaps the respective frame positions of the first and second candidate objects identified in (a).
Claim 9
Dependent Claim
60 words
A method according to claim 1 , wherein step (c) comprises identifying that the number of candidate objects in the second frame is less than the number of candidate objects identified in the first frame, and identifying a new candidate object whose frame position partially overlaps the respective frame positions of the first and second candidate objects identified in (a).
Claim 10
Dependent Claim
26 words
A non-transitory computer readable medium having stored therein a computer program comprising instructions which, when executed on a processor, perform the steps of claim 1 .
Claim 11
Dependent Claim
213 words
An image processing system comprising: a receiver arranged to receive a sequence of frames from a video source; and a processor arranged to: (a) identify, in a first frame, first and second objects, (b) provide first and second appearance models respectively representing the first and second models; (c) identify, in a second, subsequent frame, a group object resulting from the merging of the first and second objects due to occlusion, (d) classify each pixel of the group object as representing either the first or second object, the classification comprising: (i) calculating first and second likelihood parameters respectively indicating correspondence between said pixel's appearance and the first and second appearance models; (ii) applying a first and second weighting factor to the respective likelihood parameters, said weighting factor being respectively based on and indicative of the determined depth order of the first and second objects; and (iii) identifying which of the first and second objects said pixel represents on the basis of the weighted first and second likelihood parameters; wherein the depth order of the first and second objects is determined based on determining in said first frame which of the first and second objects is nearer to a reference position in the first frame or to a reference line extending across the first frame.
Claim 12
Dependent Claim
213 words
An image processing system comprising: a receiver arranged to receive a sequence of frames from a video source; and a processor arranged to: (a) identify, in a first frame, first and second objects, (b) provide first and second appearance models respectively representing the first and second models; (c) identify, in a second, subsequent frame, a group object resulting from the merging of the first and second objects due to occlusion, (d) classify each pixel of the group object as representing either the first or second object, the classification comprising: (i) calculating first and second likelihood parameters respectively indicating correspondence between said pixel's appearance and the first and second appearance models; (ii) applying a first and second weighting factor to the respective likelihood parameters, said weighting factor being respectively based on and indicative of the determined depth order of the first and second objects; and (iii) identifying which of the first and second objects said pixel represents on the basis of the weighted first and second likelihood parameters; wherein the depth order of the first and second objects is determined based on determining in said first frame which of the first and second objects is nearer to a reference position in the first frame or to a reference line extending across the first frame.
Claim 13
Dependent Claim
25 words
A video surveillance system comprising a video source for generating frames of a video sequence and an image processing system according to claim 10 .
References Cited (Backward Citations)
US6526161B1
Cited
US20030219146A1
Cited
US20050012817A1
Cited
US20050286756A1
Cited
US20100215251A1
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2014-12-05 | 2015-06-06 | 2015-12-06 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2018-12-05 | 2019-06-06 | 2019-12-06 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2022-12-05 | 2023-06-06 | 2023-12-06 | $7700.00 | Window Closed / Lapsed |